web-dev-qa-db-fra.com

Python/Tensorflow - L'entrée pour remodeler est un tenseur avec 92416 valeurs, mais la forme demandée nécessite un multiple de 2304

J'ai la partie de code suivante pour un réseau de neurones de convolution:

import numpy as np
import matplotlib.pyplot as plt
import cifar_tools
import tensorflow as tf

data, labels = cifar_tools.read_data('C:\\Users\\abc\\Desktop\\temp')

x = tf.placeholder(tf.float32, [None, 150 * 150])
y = tf.placeholder(tf.float32, [None, 2])

w1 = tf.Variable(tf.random_normal([5, 5, 1, 64]))
b1 = tf.Variable(tf.random_normal([64]))

w2 = tf.Variable(tf.random_normal([5, 5, 64, 64]))
b2 = tf.Variable(tf.random_normal([64]))

w3 = tf.Variable(tf.random_normal([6*6*64, 1024]))
b3 = tf.Variable(tf.random_normal([1024]))

w_out = tf.Variable(tf.random_normal([1024, 2]))
b_out = tf.Variable(tf.random_normal([2]))

def conv_layer(x,w,b):
    conv = tf.nn.conv2d(x,w,strides=[1,1,1,1], padding = 'SAME')
    conv_with_b = tf.nn.bias_add(conv,b)
    conv_out = tf.nn.relu(conv_with_b)
    return conv_out

def maxpool_layer(conv,k=2):
    return tf.nn.max_pool(conv, ksize=[1,k,k,1], strides=[1,k,k,1], padding='SAME')

def model():
    x_reshaped = tf.reshape(x, shape=[-1,150,150,1])

    conv_out1 = conv_layer(x_reshaped, w1, b1)
    maxpool_out1 = maxpool_layer(conv_out1)
    norm1 = tf.nn.lrn(maxpool_out1, 4, bias=1.0, alpha=0.001/9.0, beta=0.75)

    conv_out2 = conv_layer(norm1, w2, b2)
    maxpool_out2 = maxpool_layer(conv_out2)
    norm2 = tf.nn.lrn(maxpool_out2, 4, bias=1.0, alpha=0.001/9.0, beta=0.75)

    maxpool_reshaped = tf.reshape(maxpool_out2, [-1,w3.get_shape().as_list()[0]])
    local = tf.add(tf.matmul(maxpool_reshaped, w3), b3)
    local_out = tf.nn.relu(local)

    out = tf.add(tf.matmul(local_out, w_out), b_out)
    return out

model_op = model()

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(model_op, y))
train_op = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)

correct_pred = tf.equal(tf.argmax(model_op, 1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred,tf.float32))

Je lis des images en niveaux de gris 150x150, mais je ne comprends pas l'erreur suivante:

Epoch 0
Traceback (most recent call last):
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1021, in _do_call
    return fn(*args)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1003, in _run_fn
    status, run_metadata)
  File "C:\Python35\lib\contextlib.py", line 66, in __exit__
    next(self.gen)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 469, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 92416 values, but the requested shape requires a multiple of 2304
         [[Node: Reshape_1 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](MaxPool_1, Reshape_1/shape)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "cnn.py", line 70, in <module>
    _, accuracy_val = sess.run([train_op, accuracy], feed_dict={x: batch_data, y: batch_onehot_vals})
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 766, in run
    run_metadata_ptr)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 964, in _run
    feed_dict_string, options, run_metadata)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1014, in _do_run
    target_list, options, run_metadata)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1034, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 92416 values, but the requested shape requires a multiple of 2304
         [[Node: Reshape_1 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](MaxPool_1, Reshape_1/shape)]]

Caused by op 'Reshape_1', defined at:
  File "cnn.py", line 50, in <module>
    model_op = model()
  File "cnn.py", line 43, in model
    maxpool_reshaped = tf.reshape(maxpool_out2, [-1,w3.get_shape().as_list()[0]])
  File "C:\Python35\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 2448, in reshape
    name=name)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 759, in apply_op
    op_def=op_def)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 2240, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 1128, in __init__
    self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 92416 values, but the requested shape requires a multiple of 2304
         [[Node: Reshape_1 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](MaxPool_1, Reshape_1/shape)]]

EDIT-1

Vous avez cette nouvelle erreur après avoir modifié en fonction de ces modifications:

x_reshaped = tf.reshape(x, shape=[-1,150,150,1])
batch_size = x_reshaped.get_shape().as_list()[0]

... Same code as above ...

maxpool_reshaped = tf.reshape(maxpool_out2, [batch_size, -1])

Erreur:

Traceback (most recent call last):
  File "cnn.py", line 52, in <module>
    model_op = model()
  File "cnn.py", line 45, in model
    maxpool_reshaped = tf.reshape(maxpool_out2, [batch_size, -1])
  File "C:\Python35\lib\site-packages\tensorflow\python\ops\gen_array_ops.py", line 2448, in reshape
    name=name)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 493, in apply_op
    raise err
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 490, in apply_op
    preferred_dtype=default_dtype)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 669, in convert_to_tensor
    ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\constant_op.py", line 176, in _constant_tensor_conversion_function
    return constant(v, dtype=dtype, name=name)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\constant_op.py", line 165, in constant
    tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\tensor_util.py", line 441, in make_tensor_proto
    tensor_proto.string_val.extend([compat.as_bytes(x) for x in proto_values])
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\tensor_util.py", line 441, in <listcomp>
    tensor_proto.string_val.extend([compat.as_bytes(x) for x in proto_values])
  File "C:\Python35\lib\site-packages\tensorflow\python\util\compat.py", line 65, in as_bytes
    (bytes_or_text,))
TypeError: Expected binary or unicode string, got None

EDIT-2

Après avoir effectué les modifications suivantes (en plus de supprimer batch_size:

w3 = tf.Variable(tf.random_normal([361, 256])) 
...
...
w_out = tf.Variable(tf.random_normal([256, 2]))

J'ai l'erreur suivante:

Epoch 0
W c:\tf_jenkins\home\workspace\release-win\device\cpu\os\windows\tensorflow\core\framework\op_kernel.cc:975] Invalid argument: logits and labels must be same size: logits_size=[256,2] labels_size=[1,2]
         [[Node: SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](Reshape_2, Reshape_3)]]
Traceback (most recent call last):
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1021, in _do_call
    return fn(*args)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1003, in _run_fn
    status, run_metadata)
  File "C:\Python35\lib\contextlib.py", line 66, in __exit__
    next(self.gen)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 469, in raise_exception_on_not_ok_status
    pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: logits and labels must be same size: logits_size=[256,2] labels_size=[1,2]
         [[Node: SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](Reshape_2, Reshape_3)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "cnn.py", line 73, in <module>
    _, accuracy_val = sess.run([train_op, accuracy], feed_dict={x: batch_data, y: batch_onehot_vals})
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 766, in run
    run_metadata_ptr)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 964, in _run
    feed_dict_string, options, run_metadata)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1014, in _do_run
    target_list, options, run_metadata)
  File "C:\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1034, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: logits and labels must be same size: logits_size=[256,2] labels_size=[1,2]
         [[Node: SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](Reshape_2, Reshape_3)]]

Caused by op 'SoftmaxCrossEntropyWithLogits', defined at:
  File "cnn.py", line 55, in <module>
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(model_op, y))
  File "C:\Python35\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 1449, in softmax_cross_entropy_with_logits
    precise_logits, labels, name=name)
  File "C:\Python35\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 2265, in _softmax_cross_entropy_with_logits
    features=features, labels=labels, name=name)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 759, in apply_op
    op_def=op_def)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 2240, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "C:\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 1128, in __init__
    self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): logits and labels must be same size: logits_size=[256,2] labels_size=[1,2]
         [[Node: SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](Reshape_2, Reshape_3)]]

EDIT-3

Voici comment se présente le fichier binaire (décapé) [libellé, nom de fichier, données]:

[array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1]), array(['1.jpg', '10.jpg', '2.jpg', '3.jpg', '4.jpg', '5.jpg', '6.jpg',
       '7.jpg', '8.jpg', '9.jpg'], 
      dtype='<U6'), array([[142, 138, 134, ..., 128, 125, 122],
       [151, 151, 149, ..., 162, 159, 157],
       [120, 121, 122, ..., 132, 128, 122],
       ..., 
       [179, 175, 177, ..., 207, 205, 203],
       [126, 129, 130, ..., 134, 130, 134],
       [165, 170, 175, ..., 193, 193, 187]])]

Comment puis-je résoudre ce problème?

Merci.

pythontensorflow
6
Simplicity

Venons-en à votre erreur initiale:

L'entrée pour remodeler est un tenseur avec 92416 valeurs, mais la forme demandée nécessite un multiple de 2304

En effet, vous adaptez votre code à partir d'un code avec la taille de l'image d'origine 24 * 24. La forme du tenseur après deux couches de convolution et deux couches de max-pooling est [-1, 6, 6, 64]. Cependant, comme la forme de votre image d'entrée est 150 * 150, la forme intermédiaire devient [-1, 38, 38, 64].

essayez de changer w3

w3 = tf.Variable (tf.random_normal ([38 * 38 * 64, 1024]))

Vous devriez toujours garder un œil sur votre flux de forme de tenseur.

10
Nick Zhang

L'erreur se passe ici:

maxpool_reshaped = tf.reshape(maxpool_out2, [-1,w3.get_shape().as_list()[0]])

Comme il est dit: L'entrée pour remodeler est un tenseur avec 92416 valeurs, mais la forme demandée nécessite un multiple de 2304

Sens 

w3.get_shape (). as_list () [0] = 2304 

et

maxpool_out2 a 92416 valeurs

mais 92416/2304 a un reste fractionnel, de sorte que python ne peut pas contenir le reste de manière égale dans "-1". 

Donc, vous devez revérifier les formes de w3 et ce que vous attendez de lui.

Proposition alternative mise à jour:

x_reshaped = tf.reshape(x, shape=[-1,150,150,1])
batch_size = x_reshaped.get_shape().as_list()[0]

... Same code as above ...

maxpool_reshaped = tf.reshape(maxpool_out2, [batch_size, -1])
3
Steven

J'ai fait face au même problème, j'ai essayé d'imprimer la couche de tenseur pour l'image donnée de 300 * 200 dans CNN.

Tensor("add_35:0", shape=(?, 300, 200, 16), dtype=float32)
Tensor("MaxPool_21:0", shape=(?, 100, 150, 16), dtype=float32)
Tensor("MaxPool_22:0", shape=(?, 75, 50, 32), dtype=float32)
Tensor("MaxPool_23:0", shape=(?, 38, 25, 64), dtype=float32)

En divisant chaque couche par 2 pour chaque couche, dans la couche entièrement connectée, nous pouvons essayer avec 38 * 25 * 64 (sortie de la couche précédente)

'w_fc_layer' : tf.Variable(tf.random_normal([38*38*64,1024]))
0
Sathish Ravi